0x2620/python-ox
2
1
Fork 0
Code Issues Pull requests Releases Wiki Activity

replace all CammelCase with under_score in ox

Browse source
This commit is contained in:
j 2012-08-14 16:12:43 +02:00
commit bb35daa95c
31 changed files with 242 additions and 244 deletions
Download patch file Download diff file Expand all files Collapse all files

22
ox/web/allmovie.py
View file

@ -3,7 +3,7 @@
import re
import time
from ox import strip_tags, findRe
from ox import strip_tags, find_re
from ox.cache import read_url
@ -28,22 +28,22 @@ def getData(id):
}
html = read_url(data["url"], unicode=True)
data['aka'] = parseList(html, 'AKA')
data['category'] = findRe(html, '<dt>category</dt>.*?<dd>(.*?)</dd>')
data['category'] = find_re(html, '<dt>category</dt>.*?<dd>(.*?)</dd>')
data['countries'] = parseList(html, 'countries')
data['director'] = parseEntry(html, 'directed by')
data['genres'] = parseList(html, 'genres')
data['keywords'] = parseList(html, 'keywords')
data['posters'] = [findRe(html, '<img src="(http://cps-.*?)"')]
data['posters'] = [find_re(html, '<img src="(http://cps-.*?)"')]
data['produced'] = parseList(html, 'produced by')
data['rating'] = findRe(html, 'Stars" title="(.*?) Stars"')
data['rating'] = find_re(html, 'Stars" title="(.*?) Stars"')
data['released'] = parseEntry(html, 'released by')
data['releasedate'] = parseList(html, 'release date')
data['runtime'] = parseEntry(html, 'run time').replace('min.', '').strip()
data['set'] = parseEntry(html, 'set in')
data['synopsis'] = strip_tags(findRe(html, '<div class="toggle-text" itemprop="description">(.*?)</div>')).strip()
data['synopsis'] = strip_tags(find_re(html, '<div class="toggle-text" itemprop="description">(.*?)</div>')).strip()
data['themes'] = parseList(html, 'themes')
data['types'] = parseList(html, 'types')
data['year'] = findRe(html, '<span class="year">.*?(\d+)')
data['year'] = find_re(html, '<span class="year">.*?(\d+)')
#data['stills'] = [re.sub('_derived.*?/', '', i) for i in re.compile('<a href="#" title="movie still".*?<img src="(.*?)"', re.DOTALL).findall(html)]
data['stills'] = re.compile('<a href="#" title="movie still".*?<img src="(.*?)"', re.DOTALL).findall(html)
#html = read_url("http://allmovie.com/work/%s/cast" % id, unicode=True)
@ -51,18 +51,18 @@ def getData(id):
#html = read_url("http://allmovie.com/work/%s/credits" % id, unicode=True)
#data['credits'] = parseTable(html)
html = read_url("http://allmovie.com/work/%s/review" % id, unicode=True)
data['review'] = strip_tags(findRe(html, '<div class="toggle-text" itemprop="description">(.*?)</div>')).strip()
data['review'] = strip_tags(find_re(html, '<div class="toggle-text" itemprop="description">(.*?)</div>')).strip()
return data
def getUrl(id):
return "http://allmovie.com/work/%s" % id
def parseEntry(html, title):
html = findRe(html, '<dt>%s</dt>.*?<dd>(.*?)</dd>' % title)
html = find_re(html, '<dt>%s</dt>.*?<dd>(.*?)</dd>' % title)
return strip_tags(html).strip()
def parseList(html, title):
html = findRe(html, '<dt>%s</dt>.*?<dd>(.*?)</dd>' % title.lower())
html = find_re(html, '<dt>%s</dt>.*?<dd>(.*?)</dd>' % title.lower())
r = map(lambda x: strip_tags(x), re.compile('<li>(.*?)</li>', re.DOTALL).findall(html))
if not r and html:
r = [strip_tags(html)]
@ -74,11 +74,11 @@ def parseTable(html):
lambda x: strip_tags(x).strip().replace('&nbsp;', ''),
x.split('<td width="305">-')
),
findRe(html, '<div id="results-table">(.*?)</table>').split('</tr>')[:-1]
find_re(html, '<div id="results-table">(.*?)</table>').split('</tr>')[:-1]
)
def parseText(html, title):
return strip_tags(findRe(html, '%s</td>.*?<td colspan="2"><p>(.*?)</td>' % title)).strip()
return strip_tags(find_re(html, '%s</td>.*?<td colspan="2"><p>(.*?)</td>' % title)).strip()
if __name__ == '__main__':
print getData('129689')